Mood and body language of robot tutor ‘contagious’

irobot

Mood and body language of robot tutor ‘contagious’

14 December 2015 by Webredactie Communication

Researcher Junchao Xu has shown that the mood and body language of a humanoid robot can be made recognisable to humans, and that the expression of these can have a positive effect on the interaction between robots and humans. Students attending a class given by a robot lecturer expressing a positive attitude found the class to be a resounding success. Xu obtained his doctorate with this research from TU Delft on Monday 14 December.

Body language‘Robots are increasingly going to be working with us, helping us and keeping us company. Social skills are important for these robots, to be able to work with us in harmony and to be accepted by us’, explains Dr Koen Hindriks, researcher at the Faculty of EEMCS and one of Junchao Xu’s PhD research supervisors.
Displaying emotions such as excited or sad is one of these social skills. It aids human understanding of robot behaviour and motives and increases its credibility, reliability and the lifelike quality of the robot. ‘Most research in this field focuses on facial expressions. Only a few studies, such as ours, focus on expressing emotion through the robot’s body language.’
UnnaturalWhat is new in this research is that the emotions are integrated into the robot’s function. As Hindriks explains, ‘For example, if a robot is pointing to something and then suddenly has to be ‘happy’, for example by throwing its arms in the air, that looks very unnatural. We have tried to improve on this and have integrated our new insights into a model and software that are as generally applicable as possible.


Emotional contagion‘We found that some of the main factors for expressing robot emotions are the height of the hands, the magnitude of movements, the vertical position of the robot’s head and the speed with which the robot moves. Through experimentation, we also showed that people are able to recognise the robot’s moods through its body language, even when they had not been instructed to pay attention to this. We also saw evidence of an ‘emotional contagion effect’: the emotional state of participants in the experiment matched the emotional state of the robot.
Robot tutorExpression of emotional states was investigated in a real-life situation in which a robot tutor gave a lecture to Master’s students and communicated with the audience through quiz questions in a lecture hall.
‘The robot gave the same lecture to two groups: for the first group in a positive emotional state and for the second in a negative emotional state. We saw that the mood of the participants was better when the RoboTutor was in a positive frame of mind compared to when it was in a negative frame of mind. This would suggest that expression of an emotional state can be used to influence interaction.’
The quality of the lecture and the robot’s gestures were scored more highly by the participants for the robot in the positive state. ‘This was a large effect. The students applauded the robot following the ‘positive’ lecture, and they all wanted to make a selfie with the robot afterwards. This was not the case for the other ‘negative’ group.’
Children with diabetesOne of the ways in which the results of Xu’s research are now being used is in a European project for children with diabetes. The robot tutor is now also giving talks at primary schools.
Additional information
Weblog RoboTutor – photo and video included: https://robotutor.weblog.tudelft.nl/  
Webpage SocioCognitive Robotics, with additional video of the RoboTutor.
Webpage PAL Personal Assistant for a Healthy Lifestyle)
Contact
Koen Hindriks (Interactive Intelligence, TU Delft), [url=]K.V.Hindriks@tudelft.nl[/url], +31 (0)15 27 82523.
Ilona van den Brink (TU Delft science information officer), [url=]i.vandenbrink@tudelft.nl[/url], +31 (0)15 27 84259.